swMATH ID: 31219
Software Authors: Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich
Description: SuperPoint: Self-Supervised Interest Point Detection and Description. This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision. As opposed to patch-based neural networks, our fully-convolutional model operates on full-sized images and jointly computes pixel-level interest point locations and associated descriptors in one forward pass. We introduce Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation (e.g., synthetic-to-real). Our model, when trained on the MS-COCO generic image dataset using Homographic Adaptation, is able to repeatedly detect a much richer set of interest points than the initial pre-adapted deep model and any other traditional corner detector. The final system gives rise to state-of-the-art homography estimation results on HPatches when compared to LIFT, SIFT and ORB.
Homepage: https://arxiv.org/abs/1712.07629
Dependencies: Tensorflow
Related Software: LF-Net; HPatches; TILDE; SIFT; D2-Net; SURF; GMS; ContextDesc; ASLFeat; SuperGlue; MatchNet; Key.Net; BRISK; ORB-SLAM2; KAZE Features; MegaDepth; GANDissect; COTR; MatchFormer; InLoc
Referenced in: 4 Publications

Referencing Publications by Year